defter*
defter / katalog / CS 485
CS 485

Deep Generative Networks

Image generation and manipulation algorithms with deep learning. Convolutional neural networks, generative adversarial networks. (multi-modal) image to image translation. Image inpainting. Texture synthesis. Unsupervised feature learning via image reconstruction. 3D image learning. Video generation.

Credit3
ECTS5
BölümComputer Engineering
FacultyFaculty of Engineering
PrereqCS 464

Hocalar 1 bu dönem · 1 geçmiş

Bu dönem (2025-2026 Spring) · 1 section
Ayşegül Dündar Boral
Geçmişte ders veren (1 kişi)
Doruk Öner

→ STARS müfredatı / syllabus

Materyal — 0 dosya

Bu derste henüz materyal yok.

İlk dosyayı sen ekleyebilirsin — notlar, geçmiş finaller, çözümler, cheat-sheet, ne varsa. Drive linki / PDF / ZIP / fotoğraf, hepsi olur.

Şu an: mail at, ben düzenleyip yayına alayım. Form/upload UX yakında geliyor (Kimya tasarlıyor).

↑ konuya CS 485 yaz

Müfredat detayı STARS syllabus

⚠️ FZ engelleyen şartlar

Course Learning Outcomes: Course Learning Outcome Assessment

📅 Haftalık müfredat

Introduction to Deep Generative Networks Convolutional Neural Network Architectures Generative Adversarial Networks Discovering Interpretable Latent Codes Transformers, Attention Models Image to Image Translation Multi-modal Image to Image Translation Presentations Image Inpainting Texture Synthesis Unsupervised Feature Learning via Image Reconstruction Self-supervised 3D Image Learning Video Generation Project Presentations ECTS - Workload Table: Activities Number Hours Workload Project (including preparation and presentation if applicable) 1 30 30 Individual or group work 14 2 28 Homework 1 10 10 Preparation for Midterm exam 1 10 10 Midterm exam 1 2 2 Preparation for Final exam 1 12 12 Report (including preparation and presentation if applicable) 1 10 10 Final exam 1 2 2 Course hours 14 3 42 Total Workload: 146 Total Workload / 30: 146 / 30 4.87 ECTS Credits of the Course: 5 Type of Course: Independent Study - Lecture - Project - Research Study Course Material: Lecture Notes - Multimedia - LMS (Moodle, etc) Teaching Methods: Assignment - Independent study - Discussion - Presentations - Lecturing